Generate speech in the voices of PRINTmov characters using TTS voice synthesis. Select a character, adjust dynamics, type your text, and hit Generate. Works best with short sentences.
PRINTmov Speak V0.1 Beta is a proof of concept — an early experiment in bringing PRINTmov characters into a speech synthesis. It is currently in beta, meaning features are limited and output quality may not yet fully reflect what the final product will sound like. Quality will improve as the system matures, and more characters and voice styles are planned for future updates.
Under the hood, the speaking voicebanks were built on the same audio used to build their singing voicebanks. In this beta version, your text is processed on a cloud GPU server that spins up on demand when speech is generated. The first request after a period of inactivity may take 1–3 minutes as the server wakes up; subsequent requests in the same session are faster.
Not all voicebanks currently support Dynamics adjustment. The feature will be added to more voicebanks in future versions.
PRINTmov Speak is a free beta tool. By generating or using audio created with PRINTmov Speak, you agree to the following: